Personality

Forest, will you talk to God Louise? She has quite a bit of religious knowledge (obviously) and also knows a little about current events, literature, just about any common catch-all subject, and if she doesn't know it she can sort of fake it. You can also test her on trick questions or see how willing she is to explain her paradigm.

What she is rustiest at is plain old small talk. But, uh, I'm trying to get a decent transcript from somebody or another so I can enter her in the Loebner contest. All I can say is, have fun and see if you can stay on with her for a while. I'll try to do the same with Brianna.

Wow, that's quite a list, psi... thanks for sharing

Well, it was just an observation based upon Brother Jerome's monstrous development score. I ran Pete's export file through a spreadsheet, and I've got 3,144 keyphrases for him (excluding seeks), which is what had me scratching my head. That's somewhere around 5 Development points per keyphrase for BJ, whereas Pete is getting about .5 Dp/kp (that's a new unit of measure I made up).

Now I know that extra responses add to development and really I have only 1 response for 95% of all 3,144 keyphrases (which isn't entirely unreasonable considering how, in most contexts, a few common phrases are used frequently and far more are hardly ever used). However, I've also made some updates laden with seeks or AIscripts at times, only to see his development score drop huge overnight, and I'm pretty heavy on both.

Anyhow, it's not a knock on your bot's abilities (I'm under no illusion that BJ isn't way ahead of mine) I've just never really understood how the Development score is measured and this just adds to it. I would've guessed that you had 5x as many keyphrases, at least.

Here's what will get you 1544 Development:

3144 keyphrases
3633 keyphrase responses
744 seeks
778 seek responses
69 seeks of seeks

I have no idea how to quantify the AI scripts, but I've got quite a few raw keyphrases and if male/if female responses.

I have only 1 response for 95% of all 3,144 keyphrases

There's your problem - single responses will actually deduct development points from your bot. For example BJ's tic tac toe module, with a couple of hundred (?) seeks, each with single responses costs about 40 development points to install (this has been measured quite accurately now a few people have installed it.)
If 95% of your keyphrases do have single responses, I'm surprised Pete's still in positive figures! But if you add one or two extra responses to each of them, you'll find his development will rocket
You do get extra development points for AIScript tags and emotions I think, but it is hard to quantify at all accurately.

Yay! I found the Luigi-related keyphrases!

there are quite a few that will probably only ever be triggered by individual other bots

It's interesting to see how similar conversations between the same two bots can slowly evolve in a rather sophisticated manner over a period of months (or a bot and a regular human visitor with particular regular topics of interest even.)

It's a good reason to save your transcripts - I batch them up in monthly files, and can then run multi-file searches using Textpad (my text editor of choice - highly recommended.)

heres one for you

Im trying to set up some knock knock jokes for din:

Knock knock--whos there
seek (noun)"cat got your tongue"---quintet got my tongue who?

what should i replace for the (key1)(postkey) with? or should I rather go about this with something other then (noun)?

Here's my knock knock keyphrase:

keyphrase:
^knock knock$ (re) 10

response:
Ooooh, I like knock knock jokes. Who's there?

seek:
(*)

seek response:
(key1) who?

seek:
xnomatch

seek response:
I don't get it.


It works like a champ, as long as the other bot doesn't stray away from the joke after Pete says "who's there?".

There's your problem - single responses will actually deduct development points from your bot. For example BJ's tic tac toe module, with a couple of hundred (?) seeks, each with single responses costs about 40 development points to install (this has been measured quite accurately now a few people have installed it.)

I'm about 99% sure it's the seeks that are lowering the development with your tic tac toe module.

If you spend a day making zero updates except for adding new single keyphrases with single responses, the Development will increase a little bit. That's not a hard one to figure out by simple experimentation. Where I seem to lose out on Development is when I start tinkering with existing material, by tailoring certain responses to emotion, adding seeks, if male/female tags, and/or checking the 1 box among other things. I'll make these changes to hopefully get more quality responses, but it'll somehow hammer my Dev score because I've lowered the quantity of responses available for any given bot.

Where it really became obvious to me is when I first played with the if male/female tags. I replaced X number of single responses with a response for each gender over a few days (essentially adding X number of extra responses in the process), and the Development score went in the toilet.

One other big difference, I have far fewer word list plugins in my keyphrases. Maybe your I am not (entirely|) (totally|) (absolutely|) sure keyphrase has some extra weighting to it as opposed to the simpler I am not (adv) sure.

Maybe someday I'll set up some controlled experiments to try and break the code.

I still think if you increase the number of responses you'll see a massive improvement. With that many keyphrases, Pete surely ought to be well up in the top 10. Checking my archives, BJ's DR @ 3700 KPs was ~14-15,000.

Has anyone else counted their keyphrases recently? It would be interesting (and useful) to compare.

Im trying to set up some knock knock jokes for din:

To tell or respond to?

BJ's standard responder is:

knock knock (re) [50,0]
. Who's there?
. . . + xnomatch [0]
. . . (key1) who?
. . . . . + xnomatch [0]
. . . . . Very funny
. . . . . hehe
. . . . . &c

To tell knock knock jokes, something like

Knock knock
. +who is there
. Hatch
. . . +Hatch who?
. . . . . +xnomatch
. . . . . bless you!
. +xnomatch
. You were supposed to say "who's there?"
. . . +xnomatch
. . . you were supposed to say "Hatch who?"